© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129533
    Prev
    Next
    INDEX
    Explanations

    free-floating or free float

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '
    1.31
    к
    0.88
    8
    0.86
    ere
    0.83
    道德
    0.81
    at
    0.80
    ak
    0.80
    𝐧
    0.79
    امة
    0.79
    erin
    0.75
    POSITIVE LOGITS
    ર
    1.20
    О
    1.17
    Ş
    1.16
    ;
    1.13
    ー
    1.10
    П
    1.09
    При
    1.09
    lere
    1.08
     sauces
    1.08
    きれい
    1.08
    Activations Density 0.000%

    No Known Activations